Mobile air conditioner control method and system

Abstract

The invention discloses a mobile air conditioner control method and system, and relates to the technical field of mobile air conditioner control. The method comprises the steps that indoor comprehensive data are collected and preprocessed; constructing an indoor three-dimensional model based on the preprocessed data, and selecting a target position; calculating the safety path cost of the mobile air conditioner from the current position to the target position by using a path planning algorithm in combination with an SLAM (Simultaneous Localization and Mapping) technology; based on the safe path cost, the surrounding environment is monitored in real time, the path is recalculated, and the air conditioner is moved to the target position; and after the mobile air conditioner arrives at the target position, the collected comprehensive data are analyzed through a machine learning model algorithm, and a personalized temperature control strategy is generated. The working parameters are adjusted in real time through the dynamic evaluation function, the optimal indoor environment is maintained, the environment change can be quickly responded, immediate feedback is provided, the flexibility and the response speed are maintained, and the comfort level of a user is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mobile air-conditioning control, and in particular to a mobile air-conditioning control method and system. Background Art

[0002] A mobile air conditioner refers to an air conditioner that can be moved at will. The air conditioner body includes a compressor, exhaust fan, electric heater, evaporator, air-cooled fin-type condenser and other devices. It is fully equipped with a power plug and four casters installed at the base of the casing, so the air conditioner can be moved at will. As a flexible and efficient cooling and heating air conditioner, compared with traditional fixed air conditioners, mobile air conditioners are not restricted by their installation location and can meet complex and changeable indoor needs. They can be used in different scenarios with their own flexibility and maneuverability, providing a wider range of applicability.

[0003] However, most traditional mobile air conditioners rely on simple temperature feedback mechanisms to work and remain at the basic functional level. They lack the ability to fully perceive the indoor environment and adjust it in an individualized manner. For example, mobile air conditioners cannot intelligently and fully consider the impact of multi-dimensional environmental factors such as humidity, light intensity, and human activity levels, resulting in user comfort not reaching the optimal state. At the same time, in terms of path planning, although mobile air conditioners have basic navigation capabilities, in complex indoor environments, such as when there are dynamic obstacles or crowded areas, existing path planning algorithms often exhibit problems such as slow response and insufficient safety.

[0004] Therefore, how to intelligently control the operation of mobile air conditioners is a technical problem that technicians currently need to solve. Summary of the invention

[0005] In view of the above-mentioned existing problems, the present invention provides a mobile air-conditioning control method and system to solve the problems of inaccurate path planning, inability to respond to environmental changes in real time and lack of personalized temperature control strategies of existing mobile air-conditioning in complex indoor environments.

[0006] In order to solve the above technical problems, the present invention provides a mobile air conditioner control method in a first aspect, comprising:

[0007] Collect comprehensive indoor data and perform pre-processing;

[0008] Build an indoor 3D model based on the preprocessed data and select the target location;

[0009] Use path planning algorithm combined with SLAM technology to calculate the safe path cost of the mobile air conditioner from the current location to the target location;

[0010] Based on the safe path cost, the surrounding environment is monitored in real time to recalculate the path and move the air conditioner to the target location;

[0011] After the mobile air conditioner reaches the target location, the collected comprehensive data is analyzed through a machine learning model algorithm to generate a personalized temperature control strategy.

[0012] In one implementation method, the indoor comprehensive data includes: point cloud data, indoor obstacle locations, air quality, indoor temperature, and indoor humidity data;

[0013] The preprocessing includes data cleaning and calibration of the indoor comprehensive data.

[0014] In one implementation method, the indoor three-dimensional model is constructed based on the preprocessed data, and the target location is selected, including the following steps:

[0015] The processed point cloud data is converted into an indoor three-dimensional mesh model through a triangulation method;

[0016] Use the semantic segmentation network to classify the indoor 3D mesh model and identify the areas of static obstacles in each part of the indoor 3D mesh model;

[0017] Generate a bounding box for the identified static obstacles and record the spatial position and range of the obstacles;

[0018] In the constructed indoor 3D model, select the target location to score the location suitability of each indoor location;

[0019] The location with the highest suitability score is selected as the final target location.

[0020] In one implementation method, the use of a path planning algorithm combined with SLAM technology to calculate the safe path cost of the mobile air conditioner from the current position to the target position includes the following steps:

[0021] Discretizing the indoor three-dimensional model into a directed graph, and updating the directed graph in real time by using SLAM technology;

[0022] The safe path cost of the mobile air conditioner from the current position to the target position is calculated by a comprehensive path cost function, and the expression of the comprehensive path cost function is:

[0023]

[0024] Among them, U(P) is the safe path cost of the mobile air conditioner from the current location to the target location, R(p i ) is the node p i Risk factors at i ,p i+1 ) is the node p i Go to the next node p i+1The mobile cost, I(P) is the information entropy of path P, q opt is the target position, |B| is the set of static obstacles, d j is the distance from the target position to the jth obstacle, P is the path, and λ1 is the control slave node p i Go to the next node p i+1 The distance parameter, p i is the node position of path P on the i-th node, p i+1 is the node position of path P at the i+1th node.

[0025] In one implementation method, the method of recalculating the path based on the safe path cost and monitoring the surrounding environment in real time includes the following steps:

[0026] According to the calculated safe path cost, the mobile air conditioner moves along the safe path to the target location;

[0027] During the movement, the indoor comprehensive data is collected and preprocessed in real time, and the preprocessed indoor comprehensive data is fused into the environmental feature vector;

[0028] Set environmental thresholds to decide whether to re-plan the path;

[0029] When the environmental feature vector exceeds the set environmental threshold, the dynamic risk of new obstacles on the path is calculated.

[0030] In one implementation method, the calculation of the dynamic risk of a new obstacle on the path includes the following steps:

[0031] The dynamic risk of new obstacles appearing on the re-planned path is calculated by the path risk function, and the safety of the re-planned path is evaluated in real time. The expression of the path risk function is:

[0032]

[0033] Where G(P) is the dynamic risk of the mobile air conditioner encountering dynamic obstacles when moving along path P, r(p i ,B) Path node p i The distance to the nearest static obstacle bounding box B, Q is the distance to the node p i Go to the next node p i+1 The average temperature change rate between avg is the average obstacle distance on the path, W is the distance between nodes p i Go to the next node p i+1 The visibility index, α1 is the distance attenuation coefficient for adjusting the node position to the target position, η7 is the parameter for controlling the average distance of the path, η8 is the parameter for controlling the visibility of the path, and ω6 is the control temperature parameter;

[0034] If the dynamic risk is lower than the preset risk threshold, the mobile air conditioner is controlled to move safely to the target location according to the re-planned path.

[0035] In one implementation method, the method of analyzing the collected comprehensive data through a machine learning model algorithm to generate a personalized temperature control strategy includes the following steps:

[0036] According to the personalized temperature control instructions set by the user, the long short-term memory network is selected as the model, and then the pre-processed indoor comprehensive data is input into the short-term memory network model to calculate the personalized temperature control strategy score. The expression is:

[0037]

[0038] Among them, C(u,q opt ) is user u at target location q opt The personalized temperature control strategy score under T is the temperature regulation power, K H is the humidity regulation power, E avg (q opt ) is the target position q opt The average energy consumption at the location, O is the current location, ω1 is the parameter for controlling the average energy consumption at the target location, and ω2 is the frequency of user activities;

[0039] The temperature and humidity are adjusted according to the personalized temperature control strategy score to obtain a personalized temperature control strategy.

[0040] A second aspect of the present invention provides a file encryption system, comprising: a data acquisition module, which collects indoor comprehensive data and performs pre-processing;

[0041] The 3D modeling module builds the indoor 3D model based on the preprocessed data and selects the target location;

[0042] The path planning module uses the path planning algorithm combined with SLAM technology to calculate the safe path cost of the mobile air conditioner from the current location to the target location;

[0043] The real-time monitoring module monitors the surrounding environment in real time and recalculates the path based on the safe path cost, so that the mobile air conditioner can reach the target location;

[0044] The temperature control strategy module, after the mobile air conditioner reaches the target location, analyzes the collected comprehensive data through a machine learning model algorithm to generate a personalized temperature control strategy.

[0045] A third aspect of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the mobile air conditioning control method as described in the first aspect of the present invention is implemented.

[0046] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the mobile air conditioner control method as described in the first aspect of the present invention is implemented.

[0047] The beneficial effects of the present invention are:

[0048] By collecting and preprocessing comprehensive indoor data, building an indoor three-dimensional model based on the processed data and selecting the best target location, the temperature, humidity and air circulation factors are considered through a comprehensive evaluation function to improve the scientific nature of the target location selection, and using the path planning algorithm combined with SLAM technology to calculate the safe path, dynamically update the directed graph to avoid static and dynamic obstacles to ensure the safety and efficiency of navigation. After reaching the target location, the historical data is analyzed through a machine learning model, and the Bayesian optimization method is used to generate a personalized temperature control strategy to meet the personalized needs of different users. At the same time, it optimizes energy utilization efficiency, continues to monitor environmental changes, and adjusts working parameters in real time through dynamic evaluation functions to maintain the optimal indoor environment. It can respond quickly to environmental changes, provide instant feedback, maintain flexibility and response speed, and significantly improve user comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0050] Figure 1 This is a flow chart of the mobile air conditioning control method in Example 1.

[0051] Figure 2 This is a system diagram of the control system of the mobile air conditioner in Example 1. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0055] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a mobile air conditioner control method, comprising the following steps:

[0056] S1. Collecting indoor comprehensive data and preprocessing includes the following steps:

[0057] The collected indoor comprehensive data includes point cloud data, indoor obstacle locations, air quality, indoor temperature and indoor humidity data, and the collected indoor comprehensive data is cleaned and calibrated;

[0058] Furthermore, for missing time series data, linear interpolation or spline interpolation methods are used to fill the gaps, and for non-time series data, the mean or median is used to fill the missing values;

[0059] Convert all types of data into a unified format for subsequent processing and analysis, and standardize the units of all data

[0060] S2, constructing an indoor three-dimensional model based on the preprocessed data, and selecting the target location includes the following steps:

[0061] The processed point cloud data is converted into an indoor three-dimensional mesh model through a triangulation method;

[0062] Use the semantic segmentation network to classify the indoor 3D mesh model and identify the areas of static obstacles in each part of the indoor 3D mesh model;

[0063] Generate a bounding box for the identified static obstacles and record the spatial position and range of the obstacles;

[0064] In the constructed indoor 3D model, select the target location to score the location suitability of each indoor location;

[0065] Furthermore, the point cloud data is converted into a polygonal mesh using a triangulation surface reconstruction algorithm, and the generated mesh is simplified, smoothed, and optimized to ensure that the mesh model is both accurate and efficient;

[0066] Input the 3D mesh model into the trained semantic segmentation network, classify each part in the model, and identify the static obstacle part from the classification results;

[0067] Calculate the distance from each location to the nearest obstacle as an important indicator for evaluating safety, extract air quality, indoor temperature and indoor humidity environmental parameters, and evaluate the comfort level of each location;

[0068] Based on the air quality, indoor temperature and humidity data, the candidate location suitability score is calculated through a comprehensive evaluation function, expressed as:

[0069]

[0070] Where S(q) is the suitability score of position q, T(q) is the temperature at position q, H(q) is the humidity at position q, D(q,B) is the distance from position q to the nearest static obstacle bounding box B, V(q) is the quality of the air at position q, and θ T is the standardized temperature value, θ H is the standardized humidity value, B is the bounding box of the static obstacle, q is the candidate position in three-dimensional coordinates, μ is the nonlinear coefficient of temperature influence, is the nonlinear coefficient of humidity, λ is the exponential decay rate of the control distance to the obstacle boundary, and η is the coefficient of adjusting the air quality at position q;

[0071] After the suitability assessment of each location is completed, the location with the highest suitability score is selected as the target location.

[0072] S3, using the path planning algorithm combined with SLAM technology to calculate the safe path cost of the mobile air conditioner from the current position to the target position includes the following steps:

[0073] The indoor three-dimensional grid model is discretized into a directed graph, and the directed graph is updated in real time through SLAM technology; the safe path cost of the mobile air conditioner from the current position to the target position is calculated through the comprehensive path cost function, and the cost of the safe path is evaluated. The expression is:

[0074]

[0075] Among them, U(P) is the cost of the safe path of the mobile air conditioner from the current location to the target location, R(p i ) is the node p i Risk factors at i ,pi+1 ) is the node p i Go to the next node p i+1 The mobile cost, I(P) is the information entropy of path P, q opt is the target position, |B| is the set of static obstacles, d j is the distance from the target position to the jth obstacle, P is the path, and λ1 is the control slave node p i Go to the next node p i+1 The distance parameter, i is the node index, j is the index of the static obstacle set |B|, p i is the node position on path P, p i+1 is the position of the next node on path P; it should be noted that the hyperbolic tangent function is a type of hyperbolic function, generally written as tanh in mathematical language; information entropy refers to the basic concept of information theory, which describes the uncertainty of possible events in the information source. Generally, the average amount of information after excluding redundancy is called "information entropy", which can solve the problem of quantitative measurement of information.

[0076] Furthermore, using SLAM technology (existing technology), as the mobile air conditioner moves in the environment, the position is continuously updated and new obstacles are detected or obstacles that no longer exist are removed; wherein, the SLAM (Simultaneous Localization and Mapping) technology refers to real-time positioning and map construction, and the problem of simultaneous positioning and mapping can be described as: the robot starts to move from an unknown position in an unknown environment, positions itself according to the position and map during the movement, and builds an incremental map based on its own positioning to achieve autonomous positioning and navigation of the robot.

[0077] The indoor three-dimensional grid model is divided into multiple cubic or hexahedral units at a fixed resolution, and each unit serves as a node;

[0078] Generate edges based on the connections between adjacent nodes to ensure that each node is connected to its surrounding neighbor nodes;

[0079] c(p i ,p i+1 ) is the node p i Move to p i+1 The cost of node movement is usually determined by the straight-line distance between the two nodes. In complex environments, terrain resistance factors need to be considered;

[0080] R(p i ) is the node p iThe risk factor at a location reflects the potential danger level of the location. If the location is close to obstacles or the ground is unstable, a higher risk value will increase the cost of passing through the node.

[0081] The distance from the target location to each static obstacle is taken into account in the path cost evaluation to ensure that the path is away from dangerous areas.

[0082] The target position is introduced and smoothed by the tanh function to ensure that the path planning tends to be close to the target position;

[0083] All candidate paths are sorted according to the calculated costs, and the path with the lowest cost is selected as the optimal path.

[0084] S4, based on the safe path cost, real-time monitoring of the surrounding environment to determine the recalculation path includes the following steps:

[0085] According to the calculated safe path cost, the mobile air conditioner moves along the safe path to the target location;

[0086] Furthermore, based on the calculated safe path cost, the mobile air conditioner's travel route is used;

[0087] The processed indoor comprehensive data is integrated into an environmental feature vector, which comprehensively reflects the current environmental status. As the mobile air conditioner moves forward, the environmental feature vector is continuously updated to reflect the latest environmental changes;

[0088] T(F(t))=β·(max(F(t))-min(F(t)));

[0089] Wherein, T(F(t)) is the fluctuation value of the environmental characteristic vector F(t), F(t) is the environmental characteristic vector, max(F(t)) is the maximum value of the environmental characteristic vector, min(F(t)) is the minimum value of the environmental characteristic vector, and β is the proportional coefficient of the control trigger sensitivity;

[0090] During the movement, the indoor comprehensive data is collected and processed, and the processed indoor comprehensive data is fused into an environmental feature vector;

[0091] The environmental threshold γ is set based on historical data analysis and experimental results to decide whether to replan the path. When T(F(t)) is greater than γ, it indicates that the environment has changed significantly, affecting the safety of the path, and it is necessary to calculate the risk of new obstacles on the path.

[0092] S5. According to the risk of new obstacles on the path, the mobile air conditioner reaches the target location, including the following steps:

[0093] The risk of new obstacles on the re-planned path is calculated through the path risk function, the safety of the current path is evaluated in real time, and the path is optimized. The expression is:

[0094]

[0095] Where G(P) is the risk of the mobile air conditioner encountering a dynamic obstacle when moving along path P, r(p i ,B) Path node p i The distance to the nearest static obstacle bounding box B, Q is the distance to the node p i Go to the next node p i+1 The average temperature change rate between avg is the average obstacle distance on the path, W is the distance between nodes p i Go to the next node p i+1 The visibility index, α1 is the distance attenuation coefficient for adjusting the node position to the target position, η7 is the parameter for controlling the average distance of the path, η8 is the parameter for controlling the visibility of the path, and ω6 is the control temperature parameter;

[0096] The mobile air conditioner moves along the path and avoids the risk of obstacles appearing on the path, and the mobile air conditioner reaches the target location safely;

[0097] Furthermore, a bounding box is generated for each newly appeared obstacle, its spatial position, size and category are recorded, and it is included in the directed graph;

[0098] For new obstacles discovered locally, priority is given to making fine adjustments near the current location to avoid drastically changing the overall path;

[0099] When local adjustments cannot meet the planned safe path, replan the entire path to ensure that all high-risk areas are avoided;

[0100] During the movement, the current location information is continuously obtained through sensors to ensure that the mobile air conditioner moves along the optimized path;

[0101] When the mobile air conditioner approaches the target location, confirm that the mobile air conditioner has accurately reached the target location.

[0102] S6. After the mobile air conditioner reaches the target location, the collected comprehensive data is analyzed by the machine learning model algorithm to generate a personalized temperature control strategy including the following steps:

[0103] After the mobile air conditioner arrives at the target location, according to the needs of the personalized temperature control strategy, the long short-term memory network is selected as the model, and then the processed indoor comprehensive data is input into the short-term memory network model to calculate the personalized temperature control strategy score. The expression is:

[0104]

[0105] Among them, C(u,q opt ) is the feature user u at the target location q opt The personalized temperature control strategy score under T is the temperature regulation power, K H is the humidity regulation power, E avg (q opt ) is the target position q opt The average energy consumption at the location, O is the current location, ω1 is the parameter for controlling the average energy consumption at the target location, and ω2 is the frequency of user activities;

[0106] According to the adjustment of temperature and humidity in the personalized temperature control strategy score, a personalized temperature control strategy is obtained;

[0107] Furthermore, after the mobile air conditioner reaches the target location, it continues to collect comprehensive indoor data;

[0108] Select the long short-term memory network and use the processed indoor comprehensive data as the input features of the long short-term memory network model;

[0109] According to the temperature adjustment power in the personalized temperature control strategy score, decide whether to adjust the temperature setting value to achieve a balance between user comfort and energy consumption. According to the humidity adjustment power in the personalized temperature control strategy score, decide whether to adjust the humidity setting value to ensure that the air humidity is appropriate. opt -O∥ controls the influence of the distance from the current position to the target position on the score. The score weight decreases when it is close to the target position.

[0110] When the average energy consumption in the personalized temperature control strategy score is high, energy-saving measures are prioritized to reduce unnecessary adjustment power;

[0111] If the user activity frequency is high, give priority to user comfort and increase the adjustment power appropriately to ensure that the environmental conditions meet the user's needs;

[0112] The generated personalized temperature control strategy is applied to the mobile air conditioner to start adjusting the temperature and humidity to ensure that the environmental conditions at the target location meet user needs.

[0113] This embodiment also provides a file encryption system, including: a data collection and preprocessing module, collecting indoor comprehensive data and performing preprocessing;

[0114] Data acquisition module, collects comprehensive indoor data and performs preprocessing;

[0115] The 3D modeling module builds the indoor 3D model based on the preprocessed data and selects the target location;

[0116] The path planning module uses the path planning algorithm combined with SLAM technology to calculate the safe path cost of the mobile air conditioner from the current location to the target location;

[0117] The real-time monitoring module monitors the surrounding environment in real time and recalculates the path based on the safe path cost, so that the mobile air conditioner can reach the target location;

[0118] The temperature control strategy module, after the mobile air conditioner reaches the target location, analyzes the collected comprehensive data through a machine learning model algorithm to generate a personalized temperature control strategy.

[0119] This embodiment also provides a computer device, which is applicable to the mobile air conditioning control method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the mobile air conditioning control method proposed in the above embodiment.

[0120] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0121] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the mobile air conditioner control method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0122] In summary, the present invention collects and preprocesses comprehensive indoor data, builds an indoor three-dimensional model based on the processed data and selects the best target position, considers temperature, humidity and air circulation factors through a comprehensive evaluation function, improves the scientific nature of target position selection, calculates a safe path using a path planning algorithm combined with SLAM technology, dynamically updates a directed graph to avoid static and dynamic obstacles, and ensures the safety and efficiency of navigation. After reaching the target position, historical data is analyzed through a machine learning model, and a personalized temperature control strategy is generated using a Bayesian optimization method to meet the personalized needs of different users. At the same time, energy utilization efficiency is optimized, environmental changes continue to be monitored, and working parameters are adjusted in real time through a dynamic evaluation function to maintain the optimal indoor environment. It can quickly respond to environmental changes, provide instant feedback, maintain flexibility and response speed, and significantly improve user comfort.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A mobile air conditioner control method, characterized in that: include: Collect comprehensive indoor data and perform pre-processing; Build an indoor 3D model based on the preprocessed data and select the target location; Use path planning algorithm combined with SLAM technology to calculate the safe path cost of the mobile air conditioner from the current location to the target location; Based on the safe path cost, the surrounding environment is monitored in real time to recalculate the path and move the air conditioner to the target location; After the mobile air conditioner reaches the target location, the collected comprehensive data is analyzed through a machine learning model algorithm to generate a personalized temperature control strategy.

2. The mobile air conditioner control method according to claim 1, characterized in that: The indoor comprehensive data includes: point cloud data, indoor obstacle locations, air quality, indoor temperature and indoor humidity data; The preprocessing includes data cleaning and calibration of the indoor comprehensive data.

3. The mobile air conditioner control method according to claim 2, characterized in that: The method of constructing an indoor three-dimensional model based on the preprocessed data and selecting a target location comprises the following steps: The processed point cloud data is converted into an indoor three-dimensional mesh model through a triangulation method; Use the semantic segmentation network to classify the indoor 3D mesh model and identify the areas of static obstacles in each part of the indoor 3D mesh model; Generate a bounding box for the identified static obstacles and record the spatial position and range of the obstacles; In the constructed indoor 3D model, select the target location to score the location suitability of each indoor location; The location with the highest suitability score is selected as the final target location.

4. The mobile air conditioner control method according to claim 3, characterized in that: The method of using a path planning algorithm in combination with SLAM technology to calculate the safe path cost of the mobile air conditioner from the current position to the target position includes the following steps: Discretizing the indoor three-dimensional model into a directed graph, and updating the directed graph in real time by using SLAM technology; The safe path cost of the mobile air conditioner from the current position to the target position is calculated by a comprehensive path cost function, and the expression of the comprehensive path cost function is: Among them, U(P) is the safe path cost of the mobile air conditioner from the current location to the target location, R(p i ) is the node p i Risk factors at i ,p i+1 ) is the node p i Go to the next node p i+1 The mobile cost, I(P) is the information entropy of path P, q opt is the target position, |B| is the set of static obstacles, d j is the distance from the target position to the jth obstacle, P is the path, and λ1 is the control slave node p i Go to the next node p i+1 The distance parameter, p i is the node position of path P on the i-th node, p i+1 is the node position of path P at the i+1th node.

5. The mobile air conditioner control method according to claim 4, characterized in that: The method of recalculating the path based on the safe path cost and monitoring the surrounding environment in real time includes the following steps: According to the calculated safe path cost, the mobile air conditioner is controlled to move toward the target location along the safe path; During the movement, the indoor comprehensive data is collected and preprocessed in real time, and the preprocessed indoor comprehensive data is fused into the environmental feature vector; Set environmental thresholds to decide whether to re-plan the path; When the environmental feature vector exceeds the set environmental threshold, the dynamic risk of new obstacles on the path is calculated.

6. The mobile air conditioner control method according to claim 5, characterized in that: The step of calculating the dynamic risk of a new obstacle on the path comprises the following steps: The dynamic risk of new obstacles appearing on the re-planned path is calculated by the path risk function, and the safety of the re-planned path is evaluated in real time. The expression of the path risk function is: Where G(P) is the dynamic risk of the mobile air conditioner encountering dynamic obstacles when moving along path P, r(p i ,B) Path node p i The distance to the nearest static obstacle bounding box B, Q is the distance to the node p i Go to the next node p i+1 The average temperature change rate between avg is the average obstacle distance on the path, W is the distance between nodes p i Go to the next node p i+1 The visibility index, α1 is the distance attenuation coefficient for adjusting the node position to the target position, η7 is the parameter for controlling the average distance of the path, η8 is the parameter for controlling the visibility of the path, and ω6 is the control temperature parameter; If the dynamic risk is lower than the preset risk threshold, the mobile air conditioner is controlled to move safely to the target location according to the re-planned path.

7. The mobile air conditioner control method according to claim 6, characterized in that: The method of analyzing the collected comprehensive data through the machine learning model algorithm to generate a personalized temperature control strategy includes the following steps: According to the personalized temperature control instructions set by the user, the long short-term memory network is selected as the model, the preprocessed indoor comprehensive data is input into the short-term memory network model, and the personalized temperature control strategy score is calculated. The expression is: Among them, C(u,q opt ) is user u at target location q opt The personalized temperature control strategy score under T is the temperature regulation power, K H is the humidity regulation power, E avg (q opt ) is the target position q opt The average energy consumption at the location, O is the current location, ω1 is the parameter for controlling the average energy consumption at the target location, and ω2 is the frequency of user activities; The temperature and humidity are adjusted according to the personalized temperature control strategy score to obtain a personalized temperature control strategy.

8. A mobile air conditioning control system, based on the mobile air conditioning control method according to any one of claims 1 to 7, characterized in that: include, Data acquisition module, collects comprehensive indoor data and performs preprocessing; The 3D modeling module builds the indoor 3D model based on the preprocessed data and selects the target location; The path planning module uses the path planning algorithm combined with SLAM technology to calculate the safe path cost of the mobile air conditioner from the current location to the target location; The real-time monitoring module monitors the surrounding environment in real time and recalculates the path based on the safe path cost, so that the mobile air conditioner can reach the target location; The temperature control strategy module, after the mobile air conditioner reaches the target location, analyzes the collected comprehensive data through a machine learning model algorithm to generate a personalized temperature control strategy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, it is used to implement the steps of the mobile air conditioner control method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it is used to implement the steps of the mobile air conditioner control method according to any one of claims 1 to 7.

Images